// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/ext2/ialloc.c
*
* Copyright (C) 1992, 1993, 1994, 1995
* Remy Card (card@masi.ibp.fr)
* Laboratoire MASI - Institut Blaise Pascal
* Universite Pierre et Marie Curie (Paris VI)
*
* BSD ufs-inspired inode and directory allocation by
* Stephen Tweedie (sct@dcs.ed.ac.uk), 1993
* Big-endian to little-endian byte-swapping/bitmaps by
* David S. Miller (davem@caip.rutgers.edu), 1995
*/
#include <linux/quotaops.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/random.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"
/*
* ialloc.c contains the inodes allocation and deallocation routines
*/
/*
* The free inodes are managed by bitmaps. A file system contains several
* blocks groups. Each group contains 1 bitmap block for blocks, 1 bitmap
* block for inodes, N blocks for the inode table and data blocks.
*
* The file system contains group descriptors which are located after the
* super block. Each descriptor contains the number of the bitmap block and
* the free blocks count in the block.
*/
/*
* Read the inode allocation bitmap for a given block_group, reading
* into the specified slot in the superblock's bitmap cache.
*
* Return buffer_head of bitmap on success or NULL.
*/
static struct buffer_head *
read_inode_bitmap(struct super_block * sb, unsigned long block_group)
{
struct ext2_group_desc *desc;
struct buffer_head *bh = NULL;
desc = ext2_get_group_desc(sb, block_group, NULL);
if (!desc)
goto error_out;
bh = sb_bread(sb, le32_to_cpu(desc->bg_inode_bitmap));
if (!bh)
ext2_error(sb, "read_inode_bitmap",
"Cannot read inode bitmap - "
"block_group = %lu, inode_bitmap = %u",
block_group, le32_to_cpu(desc->bg_inode_bitmap));
error_out:
return bh;
}
static void ext2_release_inode(struct super_block *sb, int group, int dir)
{
struct ext2_group_desc * desc;
struct buffer_head *bh;
desc = ext2_get_group_desc(sb, group, &bh);
if (!desc) {
ext2_error(sb, "ext2_release_inode",
"can't get descriptor for group %d", group);
return;
}
spin_lock(sb_bgl_lock(EXT2_SB(sb), group));
le16_add_cpu(&desc->bg_free_inodes_count, 1);
if (dir)
le16_add_cpu(&desc->bg_used_dirs_count, -1);
spin_unlock(sb_bgl_lock(EXT2_SB(sb), group));
if (dir)
percpu_counter_dec(&EXT2_SB(sb)->s_dirs_counter);
mark_buffer_dirty(bh);
}
/*
* NOTE! When we get the inode, we're the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call "clear_inode()"
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext2_free_inode (struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh;
unsigned long block_group;
unsigned long bit;
struct ext2_super_block * es;
ino = inode->i_ino;
ext2_debug ("freeing inode %lu\n", ino);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
/* Quota is already initialized in iput() */
dquot_free_inode(inode);
dquot_drop(inode);
es = EXT2_SB(sb)->s_es;
is_directory = S_ISDIR(inode->i_mode);
if (ino < EXT2_FIRST_INO(sb) ||
ino > le32_to_cpu(es->s_inodes_count)) {
ext2_error (sb, "ext2_free_inode",
"reserved or nonexistent inode %lu", ino);
return;
}
block_group = (ino - 1) / EXT2_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT2_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext2_clear_bit_atomic(sb_bgl_lock(EXT2_SB(sb), block_group),
bit, (void *) bitmap_bh->b_data))
ext2_error (sb, "ext2_free_inode",
"bit already cleared for inode %lu", ino);
else
ext2_release_inode(sb, block_group, is_directory);
mark_buffer_dirty(bitmap_bh);
if (sb->s_flags & SB_SYNCHRONOUS)
sync_dirty_buffer(bitmap_bh);
brelse(bitmap_bh);
}
/*
* We perform asynchronous prereading of the new inode's inode block when
* we create the inode, in the expectation that the inode will be written
* back soon. There are two reasons:
*
* - When creating a large number of files, the async prereads will be
* nicely merged into large reads
* - When writing out a large number of inodes, we don't need to keep on
* stalling the writes while we read the inode block.
*
* FIXME: ext2_get_group_desc() needs to be simplified.
*/
static void ext2_preread_inode(struct inode *inode)
{
unsigned long block_group;
unsigned long offset;
unsigned long block;
struct ext2_group_desc * gdp;
struct backing_dev_info *bdi;
bdi = inode_to_bdi(inode);
if (bdi_rw_congested(bdi))
return;
block_group = (inode->i_ino - 1) / EXT2_INODES_PER_GROUP(inode->i_sb);
gdp = ext2_get_group_desc(inode->i_sb, block_group, NULL);
if (gdp == NULL)
return;
/*
* Figure out the offset within the block group inode table
*/
offset = ((inode->i_ino - 1) % EXT2_INODES_PER_GROUP(inode->i_sb)) *
EXT2_INODE_SIZE(inode->i_sb);
block = le32_to_cpu(gdp->bg_inode_table) +
(offset >> EXT2_BLOCK_SIZE_BITS(inode->i_sb));
sb_breadahead(inode->i_sb, block);
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory\'s block
* group to find a free inode.
*/
static int find_group_dir(struct super_block *sb, struct inode *parent)
{
int ngroups = EXT2_SB(sb)->s_groups_count;
int avefreei = ext2_count_free_inodes(sb) / ngroups;
struct ext2_group_desc *desc, *best_desc = NULL;
int group, best_group = -1;
for (group = 0; group < ngroups; group++) {
desc = ext2_get_group_desc (sb, group, NULL);
if (!desc || !desc->bg_free_inodes_count)
continue;
if (le16_to_cpu(desc->bg_free_inodes_count) < avefreei)
continue;
if (!best_desc ||
(le16_to_cpu(desc->bg_free_blocks_count) >
le16_to_cpu(best_desc->bg_free_blocks_count))) {
best_group = group;
best_desc = desc;
}
}
return best_group;
}
/*
* Orlov's allocator for directories.
*
* We always try to spread first-level directories.
*
* If there are blockgroups with both free inodes and free blocks counts
* not worse than average we return one with smallest directory count.
* Otherwise we simply return a random group.
*
* For the rest rules look so:
*
* It's OK to put directory into a group unless
* it has too many directories already (max_dirs) or
* it has too few free inodes left (min_inodes) or
* it has too few free blocks left (min_bloc